Brain Tumor Detection Using Wavelet Transform and Convolution Neural Network in Magnetic Resonance Imaging
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The brain tumor is the growth of an abnormal mass in the brain which may be malignant or benign. Misdiagnosis of different types of brain tumors reduces the patients' chances of survival. In the last years, efforts have been made to automate the present process for clinical and research reasons. For this purpose, machine learning methods were highly considered for a long time. In this paper, we presented a method for classification of brain tumors from magnetic resonance images using a convolutional neural network and two-level discrete wavelet transform algorithm. The BRATS 2013 dataset contains FLAIR, T1, T1c and T2 images of 20 patients with high-grade glioma, and ten patients with low-grade glioma were used in this investigation. This study aimed to classify the data into two classes of high-grade glioma and low-grade glioma by convolution neural network using a two-level wavelet transform algorithm on images. The Image wavelet coefficients contain more information than the original images, thus increasing the network performance. All the experiments were performed on the main dataset and two synthetic datasets with 60 and 300 data. The highest classification accuracy is obtained for T1 images in all three sets of 30, 60 and 300 data that were 86.25%, 94.58%, and 95.86%, respectively.
Abstract
The brain tumor is the growth of an abnormal mass in the brain which may be malignant or benign. Misdiagnosis of different types of brain tumors reduces the patients' chances of survival. In the last years, efforts have been made to automate the present process for clinical and research reasons. For this purpose, machine learning methods were highly considered for a long time. In this paper, we presented a method for classification of brain tumors from magnetic resonance images using a convolutional neural network and two-level discrete wavelet transform algorithm. The BRATS 2013 dataset contains FLAIR, T1, T1c and T2 images of 20 patients with high-grade glioma, and ten patients with low-grade glioma were used in this investigation. This study aimed to classify the data into two classes of high-grade glioma and low-grade glioma by convolution neural network using a two-level wavelet transform algorithm on images. The Image wavelet coefficients contain more information than the original images, thus increasing the network performance. All the experiments were performed on the main dataset and two synthetic datasets with 60 and 300 data. The highest classification accuracy is obtained for T1 images in all three sets of 30, 60 and 300 data that were 86.25%, 94.58%, and 95.86%, respectively.
참고문헌 (23)
- Abiwinanda, N., "Brain tumor classification using convolutional neural network", World congress on medical physics and biomedical engineering 2018, pp.183~189 (2018), Springer
- Alfonse, M., "An automatic classification of brain tumors through MRI using support vector machine", Egy. Comp. Sci. J, 40(3) (2016)
- Anaraki, A. K., "Magnetic resonance imagingbased brain tumor grades classification and grading via convolutional neural networks and genetic algorithms", biocybernetics and biomedical engineering, 39(1), pp.63~74 (2019)
- Cheng, J., "Brain tumor dataset (Version 5)", ~ (2017)
- Cheng, J., "Correction: enhanced performance of brain tumor classification via tumor region augmentation and partition", PloS one, 10(12), pp.e0144479~ (2015)
- Cui, Z, "Brain MRI segmentation with patch-based CNN approach", 2016 35th Chinese Control Conference (CCC), pp.7026~7031 (2016), IEEE
- Ge, C., "3D multi-scale convolutional networks for glioma grading using MR images", 2018 25th IEEE International Conference on Image Processing (ICIP), pp.141~145 (2018), IEEE
- Havaei, M., "Brain tumor segmentation with deep neural networks", Medical image analysis, 35, pp.18~31 (2017)
- Kleesiek, J., "Deep MRI brain extraction : A 3D convolutional neural network for skull stripping", NeuroImage, 129, pp.460~469 (2016)
- Lo, C. S., "Support vector machine for breast MR image classification", Computers & Mathematics with Applications, 64(5), pp.1153~1162 (2012)
- Louis, D. N., "The 2016 World Health Organization classification of tumors of the central nervous system : a summary", Acta neuropathologica, 131(6), pp.803~820 (2016)
- Menze, B. H., "The multimodal brain tumor image segmentation benchmark(BRATS)", IEEE transactions on medical imaging, 34(10), pp.1993~2024 (2014)
- Moeskops, P., "Automatic segmentation of MR brain images with a convolutional neural network", IEEE transactions on medical imaging, 35(5), pp.1252~1261 (2016)
- Mohsen, H., "Classification using deep learning neural networks for brain tumors", Future Computing and Informatics Journal, 3(1), pp.68~71 (2018)
- Pan, Y, "Brain tumor grading based on neural networks and convolutional neural networks", 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp.699~702 (2015), IEEE
- Rasti, R., "Breast cancer diagnosis in DCEMRI using mixture ensemble of convolutional neural networks", Pattern Recognition, 72, pp.381~390 (2017)
- Sajjad, M., "Multi-grade brain tumor classification using deep CNN with extensive data augmentation", Journal of computational science, 30, pp.174~182 (2019)
- Soltaninejad, M., "Brain tumour grading in different MRI protocols using SVM on statistical features" (2014)
- Sudha, B., "Classification of brain tumor grades using neural network", proceedings of the world Congress on engineering, 1, pp.2~4 (2014)
- Sultan, H. H., "Multi-classification of brain tumor images using deep neural network", IEEE Access, 7, pp.69215~69225 (2019)
- Trigui, R., "Automatic classification and localization of prostate cancer using multiparametric MRI", MRS, 2017, pp.31, 189~198
- Zhang, W., "Deep convolutional neural networks for multi-modality isointense infant brain image segmentation", NeuroImage, 108, pp.214~224 (2015)
- Zhao, L., "Deep feature learning with discrimination mechanism for brain tumor segmentation and diagnosis", 2015 international conference on intelligent information hiding and multimedia signal processing (IIH-MSP), pp.306~309 (2015), IEEE